Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on floating-point numbers (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     "'
    -0.07
    erialize
    -0.06
    oundingBox
    -0.06
     bik
    -0.06
    _iteration
    -0.06
    edores
    -0.06
     noci
    -0.06
    fit
    -0.06
    ＾
    -0.06
     \`
    -0.06
    POSITIVE LOGITS
     віднов
    0.08
     Snap
    0.07
    belum
    0.07
    (enemy
    0.07
     compact
    0.07
    .SetText
    0.07
     No
    0.07
    Snap
    0.07
    ndon
    0.06
     digs
    0.06
    Act Density 0.003%

    No Known Activations